GeForce 9650M GS vs GTX 680
Aggregate performance score
We've compared GeForce GTX 680 with GeForce 9650M GS, including specs and performance data.
GTX 680 outperforms 9650M GS by a whopping 1963% based on our aggregate benchmark results.
Contents
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 415 | 1248 |
| Place by popularity | not in top-100 | not in top-100 |
| Cost-effectiveness evaluation | 2.70 | no data |
| Power efficiency | 5.30 | 1.73 |
| Architecture | Kepler (2012−2018) | Tesla (2006−2010) |
| GPU code name | GK104 | G84 |
| Market segment | Desktop | Laptop |
| Release date | 22 March 2012 (14 years ago) | 13 March 2008 (18 years ago) |
| Launch price (MSRP) | $499 | no data |
Cost-effectiveness evaluation
The higher the ratio, the better. We use the manufacturer's recommended prices.
Performance to price scatter graph
Detailed specifications
General parameters such as number of shaders, GPU core base clock and boost clock speeds, manufacturing process, texturing and calculation speed. Note that power consumption of some graphics cards can well exceed their nominal TDP, especially when overclocked.
| Pipelines / CUDA cores | 1536 | 32 |
| Core clock speed | 1006 MHz | 625 MHz |
| Boost clock speed | 1058 MHz | no data |
| Number of transistors | 3,540 million | 289 million |
| Manufacturing process technology | 28 nm | 80 nm |
| Power consumption (TDP) | 195 Watt | 29 Watt |
| Texture fill rate | 135.4 | 10.00 |
| Floating-point processing power | 3.25 TFLOPS | 0.08 TFLOPS |
| ROPs | 32 | 8 |
| TMUs | 128 | 16 |
| L1 Cache | 128 KB | no data |
| L2 Cache | 512 KB | 32 KB |
Form factor & compatibility
Information on compatibility with other computer components. Useful when choosing a future computer configuration or upgrading an existing one. For desktop graphics cards it's interface and bus (motherboard compatibility), additional power connectors (power supply compatibility).
| Laptop size | no data | large |
| Bus support | PCI Express 3.0 | no data |
| Interface | PCIe 3.0 x16 | PCIe 2.0 x16 |
| Length | 256 mm | no data |
| Height | 4.376" (11.1 cm) | no data |
| Width | 2-slot | no data |
| Supplementary power connectors | 2x 6-pin | None |
| SLI options | + | - |
VRAM capacity and type
Parameters of VRAM installed: its type, size, bus, clock and resulting bandwidth. Integrated GPUs have no dedicated video RAM and use a shared part of system RAM.
| Memory type | GDDR5 | GDDR3 |
| Maximum RAM amount | 2048 MB | 512 MB |
| Memory bus width | 256-bit GDDR5 | 128 Bit |
| Memory clock speed | 1502 MHz | 800 MHz |
| Memory bandwidth | 192.2 GB/s | 25.6 GB/s |
| Shared memory | - | - |
Connectivity and outputs
This section shows the types and number of video connectors on each GPU. The data applies specifically to desktop reference models (for example, NVIDIA’s Founders Edition). OEM partners often modify both the number and types of ports. On notebook GPUs, video‐output options are determined by the laptop’s design rather than the graphics chip itself.
| Display Connectors | One Dual Link DVI-I, One Dual Link DVI-D, One HDMI, One DisplayPort | No outputs |
| Multi monitor support | 4 displays | no data |
| HDMI | + | - |
| HDCP | + | - |
| Maximum VGA resolution | 2048x1536 | no data |
| Audio input for HDMI | Internal | no data |
API and SDK support
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 (11_0) | 11.1 (10_0) |
| Shader Model | 6.5 (5.1) | 4.0 |
| OpenGL | 4.2 | 3.3 |
| OpenCL | 3.0 | 1.1 |
| Vulkan | 1.2.175 | N/A |
| CUDA | + | 1.1 |
Synthetic benchmarks
Non-gaming benchmark results comparison. The combined score is measured on a 0-100 point scale.
Combined synthetic benchmark score
This is our combined benchmark score.
Passmark
This is the most ubiquitous GPU benchmark. It gives the graphics card a thorough evaluation under various types of load, providing four separate benchmarks for Direct3D versions 9, 10, 11 and 12 (the last being done in 4K resolution if possible), and few more tests engaging DirectCompute capabilities.
3DMark Vantage Performance
3DMark Vantage is an outdated DirectX 10 benchmark using 1280x1024 screen resolution. It taxes the graphics card with two scenes, one depicting a girl escaping some militarized base located within a sea cave, the other displaying a space fleet attack on a defenseless planet. It was discontinued in April 2017, and Time Spy benchmark is now recommended to be used instead.
Gaming performance
Let's see how good the compared graphics cards are for gaming. Particular gaming benchmark results are measured in FPS.
Average FPS across all PC games
Here are the average frames per second in a large set of popular games across different resolutions:
| 900p | 45
+2150%
| 2−3
−2150%
|
| Full HD | 75
+2400%
| 3−4
−2400%
|
| 4K | 25
+2400%
| 1−2
−2400%
|
Cost per frame, $
| 1080p | 6.65 | no data |
| 4K | 19.96 | no data |
FPS performance in popular games
Full HD
Low
| Counter-Strike 2 | 75−80
+2433%
|
3−4
−2433%
|
| Cyberpunk 2077 | 27−30
+2700%
|
1−2
−2700%
|
| Resident Evil 4 Remake | 27−30
+2700%
|
1−2
−2700%
|
Full HD
Medium
| Battlefield 5 | 55−60
+2850%
|
2−3
−2850%
|
| Counter-Strike 2 | 75−80
+2433%
|
3−4
−2433%
|
| Cyberpunk 2077 | 27−30
+2700%
|
1−2
−2700%
|
| Far Cry 5 | 40−45 | 0−1 |
| Fortnite | 75−80
+2500%
|
3−4
−2500%
|
| Forza Horizon 4 | 55−60
+1040%
|
5−6
−1040%
|
| Forza Horizon 5 | 40−45
+2000%
|
2−3
−2000%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 50−55
+525%
|
8−9
−525%
|
| Valorant | 110−120
+314%
|
27−30
−314%
|
Full HD
High
| Battlefield 5 | 55−60
+2850%
|
2−3
−2850%
|
| Counter-Strike 2 | 75−80
+2433%
|
3−4
−2433%
|
| Counter-Strike: Global Offensive | 224
+1079%
|
18−20
−1079%
|
| Cyberpunk 2077 | 27−30
+2700%
|
1−2
−2700%
|
| Dota 2 | 85−90
+642%
|
12−14
−642%
|
| Far Cry 5 | 40−45 | 0−1 |
| Fortnite | 75−80
+2500%
|
3−4
−2500%
|
| Forza Horizon 4 | 55−60
+1040%
|
5−6
−1040%
|
| Forza Horizon 5 | 40−45
+2000%
|
2−3
−2000%
|
| Grand Theft Auto V | 56
+2700%
|
2−3
−2700%
|
| Metro Exodus | 27−30 | 0−1 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 50−55
+525%
|
8−9
−525%
|
| The Witcher 3: Wild Hunt | 42
+600%
|
6−7
−600%
|
| Valorant | 110−120
+314%
|
27−30
−314%
|
Full HD
Ultra
| Battlefield 5 | 55−60
+2850%
|
2−3
−2850%
|
| Cyberpunk 2077 | 27−30
+2700%
|
1−2
−2700%
|
| Dota 2 | 85−90
+642%
|
12−14
−642%
|
| Far Cry 5 | 40−45 | 0−1 |
| Forza Horizon 4 | 55−60
+1040%
|
5−6
−1040%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 50−55
+525%
|
8−9
−525%
|
| The Witcher 3: Wild Hunt | 22
+267%
|
6−7
−267%
|
| Valorant | 110−120
+314%
|
27−30
−314%
|
Full HD
Epic
| Fortnite | 75−80
+2500%
|
3−4
−2500%
|
1440p
High
| Counter-Strike 2 | 24−27
+767%
|
3−4
−767%
|
| Counter-Strike: Global Offensive | 100−110
+3300%
|
3−4
−3300%
|
| Grand Theft Auto V | 21−24
+2000%
|
1−2
−2000%
|
| Metro Exodus | 16−18 | 0−1 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 120−130
+1657%
|
7−8
−1657%
|
| Valorant | 140−150
+2267%
|
6−7
−2267%
|
1440p
Ultra
| Battlefield 5 | 35−40
+3700%
|
1−2
−3700%
|
| Cyberpunk 2077 | 12−14 | 0−1 |
| Far Cry 5 | 30−33
+2900%
|
1−2
−2900%
|
| Forza Horizon 4 | 30−35
+1550%
|
2−3
−1550%
|
| The Witcher 3: Wild Hunt | 20−22
+900%
|
2−3
−900%
|
1440p
Epic
| Fortnite | 30−33
+2900%
|
1−2
−2900%
|
4K
High
| Counter-Strike 2 | 10−11 | 0−1 |
| Grand Theft Auto V | 21
+50%
|
14−16
−50%
|
| Metro Exodus | 10−11 | 0−1 |
| The Witcher 3: Wild Hunt | 16 | 0−1 |
| Valorant | 70−75
+2367%
|
3−4
−2367%
|
4K
Ultra
| Battlefield 5 | 18−20 | 0−1 |
| Counter-Strike 2 | 10−11 | 0−1 |
| Cyberpunk 2077 | 5−6 | 0−1 |
| Dota 2 | 45−50
+2350%
|
2−3
−2350%
|
| Far Cry 5 | 14−16 | 0−1 |
| Forza Horizon 4 | 24−27
+2300%
|
1−2
−2300%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 12−14
+550%
|
2−3
−550%
|
4K
Epic
| Fortnite | 12−14
+550%
|
2−3
−550%
|
This is how GTX 680 and 9650M GS compete in popular games:
- GTX 680 is 2150% faster in 900p
- GTX 680 is 2400% faster in 1080p
- GTX 680 is 2400% faster in 4K
Here's the range of performance differences observed across popular games:
- in Counter-Strike: Global Offensive, with 1440p resolution and the High Preset, the GTX 680 is 3300% faster.
All in all, in popular games:
- Without exception, GTX 680 surpassed 9650M GS in all 28 of our tests.
Pros & cons summary
| Performance score | 13.41 | 0.65 |
| Recency | 22 March 2012 | 13 March 2008 |
| Maximum RAM amount | 2048 MB | 512 MB |
| Chip lithography | 28 nm | 80 nm |
| Power consumption (TDP) | 195 Watt | 29 Watt |
GTX 680 has a 1963% higher aggregate performance score, an age advantage of 4 years, a 300% higher maximum VRAM amount, and a 186% more advanced lithography process.
9650M GS, on the other hand, has 572% lower power consumption.
The GeForce GTX 680 is our recommended choice as it beats the GeForce 9650M GS in performance tests.
Be aware that GeForce GTX 680 is a desktop graphics card while GeForce 9650M GS is a notebook one.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
